© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 2697
    Prev
    Next
    INDEX
    Explanations

    instances where the concept of time is mentioned in relation to past duration

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the time elapsed since past events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pert
    -0.79
    acus
    -0.71
    rongh
    -0.67
    ortment
    -0.66
    ulkan
    -0.65
    andom
    -0.63
    uras
    -0.61
    olean
    -0.60
    ulner
    -0.60
     uncond
    -0.59
    POSITIVE LOGITS
     enough
    0.92
    aneously
    0.84
     ago
    0.81
     Enough
    0.77
    Enough
    0.69
     mornings
    0.66
    aneous
    0.66
    eners
    0.65
    ÑĤ
    0.64
     anymore
    0.64
    Activations Density 0.037%

    No Known Activations